搜档网
当前位置:搜档网 › Lyman Alpha Emitters at Redshift 5.7 in the COSMOS Field

Lyman Alpha Emitters at Redshift 5.7 in the COSMOS Field

Lyman Alpha Emitters at Redshift 5.7 in the COSMOS Field
Lyman Alpha Emitters at Redshift 5.7 in the COSMOS Field

a r X i v :a s t r o -p h /0702458v 1 18 F e

b 2007

Draft version February 5,2008

Preprint typeset using L A T E X style emulateapj v.10/09/06

LYMAN αEMITTERS AT REDSHIFT 5.7IN THE COSMOS FIELD

1

T.Murayama 2,Y.Taniguchi 3,N.Z.Scoville 4,5,M.Ajiki 2,D.B.Sanders 5,B.Mobasher 6,H.Aussel 5,7,P.

Capak 4,A.Koekemoer 6,Y.Shioya 3,T.Nagao 8,9,C.Carilli 10,R.S.Ellis 4,B.Garilli 11,M.Giavalisco 6,M.G.Kitzbichler 12,O.LeFevre 13,D.Maccagni 11,E.Schinnerer 14,V.Smolcic 15,16,S.Tribiano 17,18,A.Cimatti

9

,Y.Komiyama 8,S.Miyazaki 19,S.S.Sasaki 2,4,J.Koda 4,and H.Karoji 8

Draft version February 5,2008

ABSTRACT

We present results from a narrow-band optical survey of a contiguous area of 1.95deg 2,covered by the Cosmic Evolution Survey (COSMOS).Both optical narrow-band (λc =8150?A and ?λ=120?A )

and broad-band (B ,V ,g ′,r ′,i ′,and z ′

)imaging observations were performed with the Subaru prime-focus camera,Suprime-Cam on the Subaru Telescope.We provide the largest contiguous narrow-band survey,targetting Ly αemitters (LAEs)at z ≈5.7.We ?nd a total of 119LAE candidates at z ~5.7.Over the wide-area covered by this survey,we ?nd no strong evidence for large scale clustering of LAEs.We estimate a star formation rate (SFR)density of ~7×10?4M ⊙yr ?1Mpc ?3for LAEs at z ≈5.7,and compare it with previous measurements.

Subject headings:cosmology:observations —cosmology:early universe —galaxies:formation —

galaxies:evolution

1.INTRODUCTION

Understanding of the formation and early evolution of galaxies requires study of rest-frame properties of well-de?ned samples of high-redshift galaxies.These are needed to address the comsic star formation history and growth of large scale structures in the early Universe and the source of cosmic reionization of intergalactic space.There are two widely used techniques to select such high-redshift galaxies:(1)Lyman Break technique,aiming for Lyman Break Galaxies (LBGs;Steidel et al.1999;Iwata

1

Based on data collected at the Subaru Telescope,which is op-erated by the National Astronomical Observatory of Japan

2Astronomical Institute,Graduate School of Science,Tohoku University,Aramaki,Aoba,Sendai 980-8578,Japan

3Physics Department,Graduate School of Science &Engineer-ing,Ehime University,2-5Bunkyo-cho,Matsuyama 790-8577,Japan

4Department of Astronomy,MS 105-24,California Institute of Technology,Pasadena,CA 91125

5Institute for Astronomy,University of Hawaii,2680Woodlawn Drive,HI 96822

6Space Telescope Science Institute,3700San Martin Drive,Bal-timore,MD 21218

7CEA Saclay,DSM/DAPNIA/SAp,91191Gif-sur-Yvette Cedex,France

8National Astronomical Observatory of Japan,2-21-1,Osawa,Mitaka,Tokyo 181-8588,Japan

9INAF —Osservatorio Astro?sico di Arcetri,Largo Enrico Fermi 5,50125Firenze,Italy

10National Radio Astronomy Observatory,P.O.Box 0,Socorro,NM 87801-0387

11INAF,Istituto di Astro?sica Spaziale e Fisica Cosmica,Sezione di Milano,via Bassini 15,20133Milano 12Max-Planck-Institut f¨u r Astrophysik,D-85748Garching bei M¨u nchen,Germany

13Laboratoire d’Astrophysique de Marseille,BP 8,Traverse du Siphon,13376Marseille Cedex 12,France 14Max Planck Institut f¨u r Astronomie,K¨o nigstuhl 17,Heidel-berg,D-69117,Germany

15Princeton University Observatory,Princeton,NJ 08544

16University of Zagreb,Department of Physics,Bijenicka cesta 32,10000Zagreb,Croatia

17American Museum of Natural History

18CUNY Bronx Community College,New York,NY

19Subaru Telescope,National Astronomical Observatory of Japan,650N.A’ohoku Place,Hilo,HI 96720

et al.2003;Ouchi et al.2004;Bouwens &Illingworth 2006and references therein),and (2)narrow-band imag-ing surveys,targeting Ly αemitters (LAEs;Hu &McMa-hon 1996;Rhoads &Malhotra 2001;Ajiki et al.2003;Hu et al.2004;Taniguchi et al.2005and references therein).The narrow-band surveys are mainly aimed at star-forming population while Lyman Break technique also selects galaxies with older age.

Recently,LAE surveys have extended study of the clus-tering and morphology of star-forming galaxies to the highest redshifts (Shimasaku et al.2004;Ouchi et al.2005;Ajiki et al.2006;Mobasher et al.2006).Indeed,some of the previous LAE surveys have shown signs of large scale structures,either using 2-D projected distri-bution of galaxies or 3-D distribution,also using red-shifts.For example,evidence for clustering of LAEs at z ≈4.9was found over an area of ?0.5degree ×0.5degree,covered by the Subaru Deep Field (SDF)(Shi-masaku et al.2004;see also Ouchi et al.2003),extend-ing to ~20Mpc ×50Mpc.However,no such struc-tures were found for LAEs at z ≈5.7(Shimasaku et al.2006)and z ≈6.6(Taniguchi et al.2005;Kashikawa et al.2006).Although,using a spectroscopically con?rmed sample of 34LAEs at z ≈5.7,Shimasaku et al.(2006)found evidence for weak clustering.In an independent study,using a spectroscopically con?rmed sample of 19LAEs at z ≈5.7,Hu et al.(2004)found structures ex-tending to angular scales of ~60Mpc with evidence for ?lamentary structures.This result was further con?rmed by Ouchi et al.(2005)who found ?lamentary structures of size 10–40Mpc in the Subaru XMM-Newton Deep Survey (SXDS:Sekiguchi et al.2004),using a photo-metric sample of 515LAEs.In addition to the above results,based on deep narrow-band surveys in so-called “blank ?elds”,evidence has been accumulating in sup-port of clustering at z =4.1to 5.2,with a few Mpc scales around high-redshift radio galaxies (Venemans et al.2002,2004;Overzier et al.2006)and quasar SDSS J0836+0054(Zheng et al.2006;Ajiki et al.2006b).These studies are useful in investigating early forma-

2Murayama et al.

tion of galaxies and large-scale structures.Furthermore, they provide important constraints on both the star formation and cosmic re-ionization history.A detailed study of clustering of galaxies at high-redshifts requires deep and wide-area surveys to allow a homogeneously se-lected sample of galaxies and to minimise e?ects of cos-mic variance.This is the subject of the present paper. In this paper we present the largest survey of LAEs at z≈5.7,covering the entire2square degree?eld of the Cosmic Evolution Survey(COSMOS),centered atα(J2000.0)=10h00m28.6s andδ(J2000.0)= +02?12′21.0′′(Scoville et al.2007).The full COS-MOS?eld has been observed in I814-band with the Ad-vanced Camera for Surveys(ACS)on-board the Hubble Space Telescope(HST).In addition to the ACS data,the multi-wavelength broad and narrow-band observations were also performed using the Supreme-Cam(Miyazaki et al.2002)on the Subaru Telescope(Kaifu et al.2000; Iye et al.2004).The narrow-band?lter NB816has an e?ective wavelength ofλc=8150?A with a width ?λ=120?A(see Ajiki et al.2003for details),allowing to select LAEs in the range5.65

2.OBSERVATIONS AND SAMPLE SELECTION

2.1.Data and Source Detection

We carried out an optical narrow-band(NB816)imag-ing survey of the entire2-deg2area of the COSMOS?eld, using the Suprime-Cam on the Subaru Telescope.These observations,combined with the broad-band(B,V,g′, r′,i′,and z′)Suprime-Cam and ACS(I814)photometric data will be used to identify LAE candidates at z~5.7 and to study their properties.Details of the narrow-band and ground-based observations and data reduction are given in Taniguchi et al.(2007)and Capak et al.(2007a) and for the HST-ACS observations in Koekemoer et al. (2007).

For the ground-based observations,the seeing size varies between the exposures.The PSF size of each NB816images is between0.′′4and0.′′7.To optimize source detection in NB816,we only use exposures with PSF sizes smaller than1.′′15to construct a combined im-age.

The limiting magnitude of the NB816has a variance of~0.5mag,depending on the location on the im-age.We only con?ne our LAE search to areas with low noise where the5σlimiting magnitude with a2′′diam-eter aperture in NB816is~25.1.This corresponds to a total e?ective area of1.95deg2.The transverse co-moving area of the LAE survey at z=5.7is3.9×104 Mpc2.The FWHM of the?lter,which has a Gaussian-like shape,corresponds to a co-moving depth of45Mpc, spanning the redshift range5.65

We have performed source detection and photometry on the NB816image with SExtractor version2.3(Bertin &Arnouts1996).A source is selected as a contiguous 9-pixel area above the3σnoise level(corresponding to 26.48mag arcsec?2)on the NB816image.Photometry is performed on the NB816and the broadband images over 0.′′5,2′′,and3′′diameter apertures.To the magnitude limit of the survey[NB816(2′′φ)=25.1],we?nd~3×105sources.

2.2.Selection of LAE Candidates

Our main aim in the present survey is to identify reli-able LAE candidates at z≈5.7by?rst selecting NB816 excess objects,using the following criteria:

NB816(2′′φ)<25.1,(1) iz(2′′φ)?NB816(2′′φ)>max(0.7,3σiz?NB816),(2)

B(0.′′5φ)>29.6,(3)

g′(0.′′5φ)>29.2,(4)

V(0.′′5φ)>29.1,and(5)

r′(0.′′5φ)>29.1,(6) where iz is the continuum magnitude atλ=8150?A, estimated by linear interpolation between i′and z′?ux densities(f iz=0.57f i′+0.43f z′).The?rst criterion en-sures that objects are detected above the5σlevel in the NB816.The criterion2allows selection of emission-line objects with observed equivalent width,EW obs≥120?A.The3σof iz?NB816is estimated from the local-background noise measurement of the most noisy region in the survey area.This is illustrated in Figure1where the LAE candidates are identi?ed on iz?NB816vs. NB816color—magnitude diagram.The criteria(3),(4), (5),and(6)ensure that z≈5.7candidates are unde-tected(at≈1.5σnoise level)in B,g′,V,and r′bands. We adopt magnitudes in a0.′′5diameter aperture to avoid possible contamination by low-z foreground objects. We?nd a total of119LAE candidates at z~5.7that satisfy the above criteria and con?rm these by careful eye inspection for apparent false detections.Our?rst spec-troscopic followup observation of~50LAE candidates indicates a~95%or better con?rmation rate(Capak et al.2007b).We also?nd that there is no low-luminosity radio-loud AGN with L(1.4GHz)>6×1024W Hz?1 among our?nal LAE candidates(Carilli et al.2007). The coordinates and photometric data for the LAE can-didates are listed in Table1.All magnitudes are cor-rected for Galactic extinction;ˉE(B?V)=0.0195(Ca-pak et al.2007a).In Table1we also list emission line ?uxes and observed equivalent widths estimated from NB816and z′?ux densities in a3′′aperture.

As shown by the criterion2,the detection limit of LAEs depends on the depth of both the NB816and i′and z′band images.However,we did not impose any noise threshold on the i′and z′band images when we selected the LAE candidates.To ensure homogeneity, we make a subsample of the LAE candidates in areas with low noise,both in the i′and z′bands where the 5σlimiting magnitude over a2′′diameter aperture is brighter than25.4or24.8mag in i′and z′bands respec-tively.This subsample(hereafter,the statistical sample) contains111LAE candidates which are identi?ed by as-terisks in Table1.We use this“statistical sample”to estimate statistical properties of LAEs,including their number density and luminosity function.The size of the e?ective area corresponding to this statistical sample is reduced to1.86deg2,equivalent to3.7×104Mpc2of the transverse co-moving area at z=5.7.The survey volume for the statistical sample is1.7×106Mpc3.

LYMANαEMITTERS AT z=5.73

3.RESULTS AND DISCUSSION

3.1.Spatial Distribution and Angular Two-Point

Correlation Function

In Figure3,we show the spatial distribution of all the

LAE candidates in our sample.There appears to be little

evidence for strong clustering.When dividing the survey

area into four tiles with0.7degree×0.7degree each,

we?nd26,28,26,and31LAEs in the SW,NW,SE,

and NE quadrant respectively.Therefore,the111LAE

candidates in the statistical sample are almost randomly

distributed at least in large scale.

We derive the angular two-point correlation function

(ACF),ω(θ),for the111LAE candidates in the“sta-

tistical sample”using the estimator de?ned by Landy&

Szalay(1993)

DD(θ)?2DR(θ)+RR(θ)

w(θ)=

4Murayama et al.

We now estimate the contribution from LAEs to the star formation rate(SFR)at z≈5.7,using the following relation(Kennicutt1998;Brocklehurst1971),

SF R(Lyα)=9.1×10?43L(Lyα)M⊙yr?1,(8) where L(Lyα)is in ergs s?1.We assume Salpeter ini-tial mass function with(m lower,m upper)=(0.1M⊙,100 M⊙).

The estimated SFRs are given in the forth column of Table1.They range from5.7to28.3M⊙yr?1with a median value of9.6M⊙yr?1.The SFRs derived here can be underestimated due to the e?ect of absorption by H i gas both in the host galaxies and in the intergalactic medium and dusts in the host galaxies.SFRs indepen-dent of the absorption are estimated by the radio data; an upper limit to the mean massive star formation rate (5M⊙to100M⊙)for the LAE sample is derived as ~100M⊙yr?1(Carilli et al.2007).

The estimated SFRs from the Lyαluniomsities here are comparable to those of LAEs at z?5.7–6.6(e.g., Ajiki et al.2003;Taniguchi et al.2005).The SFR den-sity at z=5.7is estimated by summing up the Lyαluminosities of the111“statistical candidates”and cor-responds to7.2×10?4M⊙yr?1Mpc?3,similar to those obtained in previous narrow-band surveys.

It would be instructive to examine whether the SFRs derived from the Lyαluminosity here are consistent with those based on the UV continuum luminosity from the broad-band data.The observed z′magnitudes,measured over3′′aperture diameters,are converted to UV contin-uum luminosities atλ=1270?A and used to estimate the SFRs,using the relation(Kennicutt1998;see also Madau et al.1998),

SF R(UV)=1.4×10?28LνM⊙yr?1,(9) where Lνis the UV continuum luminosity in ergs s?1 Hz?1.For each object,we estimate the SFR from its rest-frame UV(λ=1270?A)continuum luminosity,with the results summarized in https://www.sodocs.net/doc/f017788502.html,parison between SF R(Lyα)and SF R(UV)in Figure6shows that,on average,SF R(UV)is relatively higher than SF R(Lyα) for most of the LAE candidates.We?nd an average ratio of SF R total(Lyα)/SF R total(UV)=0.68,where SF R total(Lyα)and SF R total(UV)are,respectively,the sum of SFRs of all our119LAE candidates from Lyαline and UV continuum.The relatively lower SF R(Lyα)compared to SF R(UV)is likely due to the e?ect of the di?erential absorption.However,some of our LAE candi-dates have SF R(Lyα)/SF R(UV)>1,e.g.,those ratios of#13,#27,#50,#71,and#114are greater than unity with2σsigni?cance.They may be in a very early phase (<108yr)of star formation activity in which SF R(UV) is underestimated(Schaerer2000;see also Nagao et al. 2004,2005).

4.SUMMARY

We have presented results from our narrow-band deep imaging survey of the COSMOS?eld,targetting LAEs at z≈5.7.This is the largest contiguous survey of LAEs. Our main results are summarized below:

(1)We found119LAE candidates in our narrow-band survey.Allowing for changes in the noise level over the entire?eld,we extracted a subsample of111LAEs that is used to make our statistical analysis.

(2)We?nd no signi?cant evidence for clustering of LAEs at z~5.7contrary to some of the previous LAE surveys.

(3)An analysis of angular two-point correlation func-tion gives the power-law relation w(θ)=A wθβ,with β=?1.2±0.2.The power-law index here is steeper than that found for Lyman break galaxies at z=4and 5.This suggests that LAEs at z≈5.7might be located in massive dark matter halos with mass of>1012M⊙.

(4)The number density of LAEs and the average star formation rate are similar to those measured in previous surveys.We estimate a star formation rate density of ~7×10?4M⊙yr?1Mpc?3at z≈5.7.

(5)We measure the Lyαluminosity function at z>5 and extend this to L(Lyα)≥1043ergs s?1,not explored by previous LAE surveys.We compare the estimated Lyαluminosity function here with those in previous stud-ies in the range z=3.4?6.6.

We would like to thank both the Subaru and HST sta?for their invaluable help.We also thank Masami Ouchi for providing us his data.This work was?nancially sup-ported in part by the Ministry of Education,Culture, Sports,Science,and Technology(Nos.10044052and 10304013),and by JSPS(15340059and17253001).SSS and TN are JSPS fellows.

REFERENCES

Ajiki,M.,et al.2003,AJ,126,2091

Ajiki,M.,Mobasher,B.,Taniguchi,Y.,Shioya,Y.,Nagao,T., Murayama,T.,&Sasaki,S.S.,2006a,ApJ,638,596

Ajiki,M.,et al.2006b,PASJ,58,499

Bertin,E.,&Arnouts,S.1996,A&AS,117,393

Bouwens,R.J.,&Illingworth,G.D.1996,Nature,443,189 Brocklehurst,M.1971,MNRAS,153,471

Capak,P.,et al.2007a,ApJ,submitted

Capak,P.,et al.2007b,in preparation

Carilli,C.L.,et al.2007,ApJ,submitted

Cowie,L.L.,&Hu,E.M.1998,AJ,115,1319

Hu,E.M.,Cowie,L.L.,Capak,P.,McMahon,R.G.,Hayashino, T.,&Komiyama,Y.2004,AJ,127,563

Hu,E.M.,&McMahon,R.G.1996,Nature,382,281

Iwata,I.,Ohta,K.,Tamura,N.,Ando,M.,Wada,S.,Watanabe,

C.,Akiyama,M.,&Aoki,K.2003,PASJ,55,415

Iye,M.,et al.2004,PASJ,56,381

Kaifu,N.,et al.2000,PASJ,52,1

Kashikawa,N.,et al.2006,ApJ,637,631Kennicutt,R.C.,Jr.1998,ARA&A,36,189

Koekemoer,A.et al.2007,ApJ,submitted

Landy,S.,&Szalay,A.S.1993,ApJ,412,64

Madau,P.,Pozzetti,L.,&Dickinson,M.1998,ApJ,498,106 Miyazaki,S.et al.2002,PASJ,54,833

Nagao,T.,et al.2004,ApJ,613,L9

Nagao,T.,et al.2005,ApJ,634,142

Ouchi,M.,et al.2003,ApJ,582,60

Ouchi,M.,et al.2004,ApJ,611,685

Ouchi,M.,et al.2005,ApJ,620,L1

Overzier,R.A.et al.2006,ApJ,637,58

Rhoads,J.E.,&Malhotra,S.2001,ApJ,563,L5

Schaerer,D.2000,in Building the Galaxies:From the Primordial Universe to the Present,eds.F.Hammer,et al.(Gif-sur-Yvette: Editions Fronti`e res),389

Scoville,N.Z.,et al.2007,ApJ,submitted

Sekiguchi,K.,et al.2004,ApSS Library,301,169

Shimasaku,K.,et al.2004,ApJ,605,L93

Shimasaku,K.,et al.2006,PASJ,58,313

LYMANαEMITTERS AT z=5.75

Steidel,C.C.,Adelberger,K.L.,Giavalisco,M.,Dickinson,M.,& Pettini,M.1999,ApJ,519,1

Taniguchi,Y.,et al.2005,PASJ,57,165

Taniguchi,Y.,et al.2007,ApJ,submitted Venemans,B.P.,et al.2002,ApJ,569,L11 Venemans,B.P.,et al.2004,A&A,424,L17 Zheng,W.,et al.2006,ApJ,640,574

6Murayama et al.

TABLE1

Photometric properties of the LAE candidates at z≈5.7

No.aα(J2000)δ(J2000)NB816b i′b z′b iz b NB816b z′b fν(NB816)c fν(z′)c f line d EW obs e (?)(?)(φ2.′′0)(φ2.′′0)(φ2.′′0)(φ2.′′0)(φ3.′′0)(φ3.′′0)(φ3.′′0)(φ3.′′0)(?A) 1*149.4786+2.211624.926.326.426.324.525.95.6±0.61.6±0.92.6±0.4353±207

2*149.5460+2.764024.826.726.026.324.625.95.0±0.71.6±1.02.3±0.5307±191 3*149.5790+1.518325.126.926.226.524.726.34.8±0.71.1±1.02.3±0.5452±401 4*149.6052+2.447623.725.225.325.223.224.818.3±0.64.3±1.08.8±0.4452±107 5*149.6320+2.346624.727.126.726.924.426.26.2±0.81.2±1.03.0±0.5578±498 6*149.6331+1.822325.027.727.327.524.726.44.7±0.7<1.02.3±0.5>498 7*149.6361+2.327624.926.526.326.424.625.65.2±0.72.2±0.92.2±0.4227±105 8*149.6537+1.539424.726.125.025.524.224.87.4±0.74.5±1.02.8±0.5136±39 9*149.6804+2.707624.827.227.227.224.630.45.4±0.8<1.02.9±0.5>659 10*149.6886+2.918024.526.025.325.624.124.68.7±0.75.0±1.13.3±0.5147±39 11149.7334+1.476524.725.725.525.624.124.88.6±0.94.5±1.43.4±0.6171±61 12*149.7362+1.559425.027.999.099.024.799.04.6±0.8<1.22.5±0.5>463 13*149.7457+2.751924.127.127.427.223.999.09.6±0.7<1.05.2±0.5>1172 14*149.7493+2.760924.125.625.425.523.625.012.9±0.73.6±1.06.0±0.5369±105 15*149.7537+2.238024.826.325.425.824.625.15.1±0.73.3±0.91.9±0.5127±47 16*149.7725+1.796725.127.227.727.424.927.53.9±0.7<1.02.0±0.5>454 17*149.7810+1.517624.625.925.825.924.225.27.6±0.93.1±1.13.3±0.6237±96 18*149.7812+1.494024.125.825.825.823.825.710.9±0.92.0±1.25.4±0.6612±385 19*149.8019+1.827424.625.726.325.924.225.97.6±0.71.6±1.13.7±0.5517±360 20*149.8023+2.225125.027.026.226.624.726.04.9±0.61.5±1.02.2±0.4344±241 21*149.8082+2.636025.127.527.027.324.827.54.6±0.8<1.02.4±0.5>529 22149.8085+1.543924.826.226.526.424.399.06.7±0.8<1.63.6±0.6>498 23*149.8186+1.720425.026.126.226.124.425.96.1±0.71.6±1.02.8±0.5387±237 24*149.8203+2.782324.526.626.426.524.326.46.9±0.7<1.13.5±0.5>669 25*149.8323+2.056125.126.926.526.724.626.75.3±0.6<0.92.6±0.4>633 26*149.8380+1.694825.126.830.227.425.128.73.5±0.6<0.91.8±0.4>473 27*149.8443+2.761524.326.226.226.224.025.89.4±0.51.8±0.74.6±0.4571±239 28*149.8466+2.751725.126.899.099.024.827.04.3±0.6<0.92.2±0.4>518 29*149.8776+2.331724.925.926.426.124.426.06.5±0.61.4±1.03.1±0.4481±328 30*149.8893+2.832224.626.426.826.624.325.87.2±0.71.7±1.13.5±0.5445±286 31*149.9107+1.614724.126.326.026.223.826.211.2±0.71.2±0.95.7±0.41031±767 32149.9197+1.482724.226.925.826.323.926.110.3±0.91.4±1.25.2±0.6851±748 33*149.9303+1.598024.526.325.425.824.225.17.5±0.83.5±1.03.1±0.5199±66 34*149.9336+2.014125.026.926.026.424.725.55.0±0.62.4±1.02.1±0.4191±88 35*149.9422+2.128624.826.126.026.124.425.66.1±0.62.1±0.82.7±0.4283±120 36*149.9447+1.535724.827.225.926.424.525.95.7±0.71.6±1.02.6±0.5375±241 37*149.9586+2.901724.627.027.427.224.499.06.4±0.7<1.23.5±0.5>667 38*149.9625+2.539724.826.930.227.524.599.05.6±0.7<1.03.1±0.5>670 39*149.9672+1.623124.426.226.126.224.226.07.8±0.61.4±0.93.8±0.4596±376 40*149.9719+2.118224.225.924.725.223.924.410.0±0.66.1±1.03.8±0.4137±27 41*149.9735+2.816624.627.228.327.524.599.05.8±0.7<1.03.2±0.5>690 42*149.9772+2.254624.927.127.127.124.827.34.4±0.6<1.12.3±0.4>479 43*149.9783+2.177624.526.526.326.424.226.17.5±0.61.4±1.03.7±0.4608±436 44*149.9792+1.789024.626.626.326.524.326.06.8±0.61.4±0.93.3±0.4518±339 45*150.0021+1.827824.826.426.026.224.525.95.8±0.61.6±0.92.7±0.4372±225 46*150.0638+1.483124.225.425.425.423.824.910.7±0.74.0±1.04.7±0.5265±75 47*150.0653+2.015624.426.225.726.024.125.28.6±0.53.0±0.93.8±0.4280±86 48*150.0710+2.769824.527.727.527.624.299.07.7±0.8<1.14.2±0.5>831 49*150.0832+2.017625.127.126.827.024.828.34.2±0.6<0.92.3±0.4>562 50*150.0937+2.684323.826.027.526.423.599.014.1±0.7<1.07.9±0.5>1744 51*150.1005+2.790124.927.299.099.024.999.04.0±0.7<1.02.7±0.5>592 52*150.1019+2.916524.626.225.525.824.225.07.3±0.73.5±1.13.0±0.5192±69 53*150.1090+1.544423.925.525.225.423.524.913.9±0.64.1±0.96.4±0.4352±84 54*150.1214+2.687725.125.999.099.024.526.95.8±0.7<1.02.9±0.5>647 55*150.1267+2.287424.827.326.727.024.526.65.5±0.6<0.92.8±0.4>649 56*150.1335+1.500625.026.625.826.124.625.95.1±0.61.6±1.02.3±0.4317±195 57*150.1376+2.259723.925.825.525.623.524.914.0±0.74.2±1.06.5±0.4344±83 58*150.1566+2.861425.028.927.728.224.899.04.2±0.7<1.02.4±0.5>523 59*150.1676+2.317724.927.627.027.324.726.34.9±0.61.1±1.02.4±0.4455±413 60*150.1919+1.576524.525.825.825.824.125.58.3±0.72.3±1.03.9±0.5374±174 61*150.2032+2.227824.325.725.025.324.024.38.9±0.66.7±0.93.0±0.4100±19 62*150.2166+2.773024.827.599.099.024.599.05.7±0.7<1.13.3±0.5>686 63*150.2254+1.543624.626.525.826.124.225.57.3±0.72.3±1.03.3±0.5320±151 64*150.2314+1.608624.927.626.627.024.525.85.8±0.61.8±0.92.6±0.4326±168 65*150.2434+1.611925.026.626.726.624.826.44.4±0.61.0±0.92.1±0.4456±413 66*150.2471+1.555524.626.524.825.424.324.56.7±0.76.0±1.02.0±0.575±22 67*150.2521+2.898023.925.424.524.923.323.717.1±0.712.6±1.25.9±0.5104±13 68*150.2623+1.862424.926.926.826.924.526.75.8±0.6<0.92.9±0.4>741 69*150.2807+1.873024.927.428.427.724.699.05.1±0.6<0.92.8±0.4>679 70150.2852+1.485824.527.028.227.424.327.56.8±0.8<1.33.6±0.6>593 71*150.2905+2.253823.525.926.025.923.325.317.6±0.62.8±0.98.8±0.4704±230 72*150.2973+2.894425.027.326.727.024.825.84.3±0.71.7±1.21.8±0.5234±169 73*150.3267+1.951124.225.726.125.824.025.78.8±0.61.9±1.04.2±0.4488±250 74*150.3400+2.800224.926.626.026.324.425.66.2±0.72.1±1.02.8±0.5294±153

LYMANαEMITTERS AT z=5.77

TABLE1—Continued

No.aα(J2000)δ(J2000)NB816b i′b z′b iz b NB816b z′b fν(NB816)c fν(z′)c f line d EW obs e (?)(?)(φ2.′′0)(φ2.′′0)(φ2.′′0)(φ2.′′0)(φ3.′′0)(φ3.′′0)(φ3.′′0)(φ3.′′0)(?A) 75*150.3493+1.933424.426.726.226.424.226.07.7±0.71.4±1.03.8±0.5602±442

76*150.3621+1.741724.328.025.926.624.025.68.8±0.62.2±0.94.2±0.4427±183 77*150.3657+2.501724.726.826.226.524.325.67.0±0.72.0±1.03.2±0.5355±184 78*150.3712+1.825023.926.125.425.823.525.014.2±0.63.5±0.96.7±0.4427±115 79*150.3795+2.518324.627.126.726.924.426.16.5±0.81.3±1.03.2±0.5530±427 80*150.3978+2.773424.826.526.426.424.325.56.6±0.72.2±1.03.0±0.5296±138 81*150.4005+1.801824.925.925.825.924.626.45.1±0.7<1.12.5±0.5>510 82*150.4078+2.911724.826.425.826.124.625.45.2±0.72.4±1.12.2±0.5200±104 83*150.4079+2.113325.026.525.926.224.725.64.8±0.72.1±0.92.0±0.4210±103 84*150.4091+2.806324.125.324.524.923.524.013.9±0.69.0±1.05.1±0.4126±17 85*150.4274+2.497424.125.825.025.423.824.511.5±0.85.8±1.04.6±0.5178±37 86*150.4339+2.486725.027.127.027.024.826.34.6±0.71.1±1.12.2±0.5429±419 87*150.4393+2.786025.126.726.526.624.725.94.8±0.71.6±1.02.2±0.4306±199 88*150.4444+1.807624.727.599.099.024.599.05.6±0.7<1.03.2±0.5>704 89*150.4685+2.707125.028.199.099.024.529.65.7±0.7<1.13.1±0.5>619 90*150.4766+1.531425.026.799.099.024.799.04.7±0.7<1.12.5±0.5>523 91*150.4890+1.688325.126.328.026.824.629.75.2±0.7<1.02.8±0.5>595 92*150.4984+2.813825.027.599.099.024.799.05.0±0.8<1.12.7±0.5>564 93*150.5114+2.764025.027.499.099.024.999.04.1±0.7<1.2.5±0.5>532 94*150.5131+1.606625.026.628.227.124.827.14.4±0.7<1.22.3±0.5>431 95*150.5362+2.087424.927.027.227.124.726.94.8±0.7<1.02.4±0.5>532 96*150.5367+1.912524.526.526.126.324.125.58.2±0.72.2±1.03.8±0.5378±167 97*150.5543+2.823024.726.826.126.424.425.66.4±0.72.1±1.02.9±0.5308±153 98*150.5677+2.577424.226.225.525.924.025.58.9±0.72.4±1.04.2±0.5388±175 99*150.5711+2.362524.926.126.326.224.626.15.2±0.61.3±1.02.5±0.4429±339 100*150.5773+1.615325.127.327.527.424.826.34.2±0.71.1±1.12.0±0.5392±389 101*150.6079+2.493525.028.299.099.024.899.04.4±0.7<1.02.9±0.5>656 102*150.6386+2.395625.127.126.726.924.726.04.6±0.71.4±1.12.1±0.5337±273 103150.6596+2.645324.727.526.627.124.426.16.5±0.71.3±0.93.2±0.5553±420 104150.6806+2.764323.926.126.726.323.726.212.3±0.71.2±0.96.3±0.51140±860 105*150.6927+1.871225.199.099.099.025.199.03.4±0.7<1.01.8±0.5>398 106*150.7034+2.739725.027.599.099.024.799.04.9±0.7<1.02.9±0.5>670 107*150.7111+2.224724.827.027.227.124.627.75.4±0.6<1.02.8±0.4>614 108*150.7150+2.234224.426.826.826.824.226.17.7±0.61.3±1.03.8±0.4623±460 109*150.7475+2.853224.626.825.826.224.325.37.1±0.92.8±1.23.1±0.6246±113 110*150.7548+2.043424.626.625.125.724.324.76.7±0.84.8±1.02.4±0.5110±34 111*150.7576+1.836524.425.825.125.423.924.310.1±0.87.0±1.23.6±0.5114±25 112*150.7722+1.861425.127.326.526.924.626.05.3±0.71.4±1.12.5±0.5396±325 113*150.7747+2.164424.926.199.099.024.699.05.4±0.7<1.13.0±0.5>617 114*150.7756+1.795324.327.099.099.024.099.09.5±0.7<1.15.1±0.5>1040 115*150.7863+2.644823.725.425.225.323.424.616.2±0.85.4±1.07.3±0.5304±58 116*150.7906+2.222225.026.826.226.524.725.44.6±0.72.6±1.01.8±0.5151±71 117150.8054+2.925024.525.825.125.424.124.88.1±1.04.3±1.53.2±0.7165±65 118*150.8211+2.249824.026.025.825.923.625.513.0±0.72.3±1.16.4±0.5631±304 119150.8342+2.339825.027.026.426.724.525.25.8±0.83.1±1.32.3±0.6164±79

a Asterisks denote the statistical sample.

b AB magnitude.An entry of“99.0”indicates that no excess?ux was measured.All of our LAE candidates are undetected in the B-,g′-,V-,r′-band data.

c Flux densities of the NB816ban

d and th

e z′band in unit of10?30erg s?1

cm?2Hz?1.Errors and upper-limits represent1σsigni?cance.d Estimated line?uxes in unit of10?17erg s?1cm?2.Errors represent1σ

signi?cance.e Estimated observed equivalent widths.Errors and lower-limits represent1σsigni?cance.

8Murayama et al.

TABLE2

Lyαluminosity and star formation rate for the LAE candidates at

z≈5.7

No.a EW0(Lyα)b L(Lyα)b SF R(Lyα)b L1270b,c SF R(UV)b SF R(Lyα)/SF R(UV)b (?A)(1042ergs s?1)(M⊙yr?1)(1028ergs s?1Hz?1)(M⊙yr?1)

1*53±319.2±1.48.4±1.38.7±4.912.1±6.80.69±0.41

2*46±298.0±1.67.3±1.58.7±5.112.1±7.20.60±0.38

3*68±608.2±1.67.4±1.56.0±5.28.4±7.20.89±0.79

4*67±1631.0±1.628.2±1.422.7±5.231.8±7.30.89±0.21

5*86±7410.7±1.79.7±1.66.1±5.28.6±7.31.14±0.98

6*>748.1±1.77.4±1.6<5.4<7.5>0.98

7*34±167.9±1.67.2±1.411.5±4.816.1±6.80.45±0.21

8*20±69.8±1.79.0±1.624.0±5.533.6±7.70.27±0.08

9*>9810.4±1.79.4±1.6<5.2<7.3>1.29

10*22±611.8±1.810.8±1.626.6±5.837.2±8.10.29±0.08

1125±912.2±2.211.1±2.023.6±7.233.1±10.10.34±0.12

12*>698.8±1.98.0±1.7<6.3<8.8>0.91

13*>17518.4±1.616.8±1.5<5.2<7.3>2.30

14*55±1621.2±1.719.3±1.519.0±5.226.6±7.30.72±0.21

15*19±76.7±1.66.1±1.517.4±4.924.3±6.90.25±0.09

16*>687.1±1.76.4±1.5<5.1<7.2>0.89

17*35±1411.7±2.010.6±1.816.3±6.022.8±8.30.47±0.19

18*91±5719.1±2.117.4±1.910.3±6.414.4±8.91.20±0.76

19*77±5413.0±1.711.9±1.58.3±5.711.7±8.01.02±0.71

20*51±368.0±1.57.2±1.47.7±5.210.7±7.20.68±0.47

21*>798.4±1.87.6±1.6<5.2<7.3>1.04

22>7412.8±2.111.7±1.9<8.5<11.9>0.98

23*58±3510.1±1.69.2±1.58.6±5.112.0±7.10.76±0.47

24*>10012.3±1.711.2±1.6<6.1<8.5>1.32

25*>949.3±1.48.5±1.3<4.9<6.8>1.24

26*>716.5±1.55.9±1.3<4.5<6.4>0.93

27*85±3616.3±1.314.8±1.19.4±3.913.2±5.41.12±0.47

28*>777.6±1.57.0±1.4<4.9<6.8>1.02

29*72±4911.1±1.410.1±1.37.6±5.110.7±7.10.95±0.64

30*66±4312.2±1.711.1±1.59.1±5.712.7±8.00.87±0.56

31*154±11420.3±1.518.5±1.46.5±4.89.1±6.72.03±1.51

32127±11218.5±2.116.8±2.07.2±6.310.1±8.81.67±1.47

33*30±1011.0±1.810.0±1.618.3±5.325.6±7.50.39±0.13

34*29±137.3±1.56.6±1.312.6±5.217.6±7.30.38±0.17

35*42±189.6±1.38.7±1.211.2±4.515.7±6.20.56±0.24

36*56±369.4±1.68.5±1.58.3±5.111.6±7.20.74±0.47

37*>10012.4±1.811.3±1.6<6.1<8.6>1.31

38*>10010.9±1.79.9±1.5<5.4<7.5>1.32

39*89±5613.6±1.412.3±1.37.5±4.710.5±6.61.17±0.74

40*20±413.3±1.512.1±1.432.3±5.145.2±7.10.27±0.05

41*>10311.2±1.710.2±1.5<5.3<7.5>1.36

42*>728.0±1.67.3±1.4<5.5<7.8>0.94

43*91±6513.2±1.512.0±1.37.2±5.110.0±7.11.20±0.86

44*77±5111.6±1.510.6±1.47.4±4.810.4±6.71.02±0.67

45*55±349.6±1.58.8±1.38.6±5.012.0±7.00.73±0.44

46*39±1116.7±1.715.2±1.620.9±5.529.3±7.70.52±0.15

47*42±1313.5±1.312.3±1.215.9±4.622.3±6.50.55±0.17

48*>12414.8±1.813.5±1.6<5.9<8.2>1.63

49*>848.0±1.47.3±1.2<4.7<6.6>1.11

50*>26027.9±1.625.4±1.5<5.3<7.4>3.43

51*>889.5±1.78.7±1.5<5.3<7.4>1.16

52*29±1010.7±1.89.7±1.618.4±5.925.8±8.20.38±0.14

53*53±1322.8±1.520.7±1.421.4±4.930.0±6.90.69±0.17

54*>9710.4±1.79.5±1.5<5.3<7.5>1.27

55*>979.8±1.58.9±1.3<5.0<7.0>1.28

56*47±298.2±1.57.5±1.48.6±5.012.0±7.10.62±0.38

57*51±1222.8±1.620.8±1.422.0±5.130.8±7.20.68±0.16

58*>788.5±1.77.8±1.5<5.4<7.6>1.03

59*68±628.3±1.57.6±1.46.1±5.48.5±7.60.89±0.81

60*56±2613.7±1.712.5±1.512.1±5.517.0±7.60.73±0.34

61*15±310.7±1.59.7±1.335.2±4.849.3±6.70.20±0.04

62*>10211.5±1.710.5±1.6<5.6<7.8>1.35

63*48±2311.8±1.610.8±1.512.2±5.517.1±7.70.63±0.30

64*49±259.4±1.48.5±1.39.5±4.713.3±6.60.64±0.33

65*68±627.4±1.46.7±1.35.3±4.77.5±6.60.90±0.81

66*11±37.1±1.76.5±1.531.5±5.344.1±7.50.15±0.04

67*15±220.8±1.818.9±1.666.3±6.392.9±8.90.20±0.03

68*>11110.4±1.49.4±1.3<4.6<6.5>1.46

69*>10110.0±1.49.1±1.3<4.9<6.8>1.33

70>8912.6±2.011.5±1.8<7.0<9.8>1.17

71*105±3431.1±1.428.3±1.314.6±4.720.5±6.61.38±0.45

72*35±256.5±1.85.9±1.69.2±6.212.9±8.70.46±0.33

LYMANαEMITTERS AT z=5.79

TABLE2—Continued

No.a EW0(Lyα)b L(Lyα)b SF R(Lyα)b L1270b,c SF R(UV)b SF R(Lyα)/SF R(UV)b (?A)(1042ergs s?1)(M⊙yr?1)(1028ergs s?1Hz?1)(M⊙yr?1)

73*73±3715.0±1.513.7±1.410.2±5.114.2±7.20.96±0.49

74*44±239.9±1.79.0±1.611.1±5.415.5±7.60.58±0.30

75*90±6613.4±1.612.2±1.57.4±5.310.3±7.41.18±0.87

76*64±2714.8±1.413.5±1.311.5±4.816.0±6.70.84±0.36

77*53±2711.5±1.610.5±1.510.7±5.315.0±7.40.70±0.36

78*64±1723.8±1.421.7±1.318.4±4.825.8±6.80.84±0.23

79*79±6411.2±1.910.2±1.77.0±5.59.8±7.71.04±0.84

80*44±2110.6±1.79.6±1.511.8±5.216.5±7.20.58±0.27

81*>768.9±1.78.1±1.6<5.7<8.0>1.00

82*30±157.7±1.87.0±1.612.7±5.917.8±8.30.39±0.20

83*31±157.1±1.66.5±1.411.2±4.915.7±6.90.41±0.20

84*19±318.1±1.516.5±1.447.5±5.166.5±7.10.25±0.03

85*27±516.4±1.814.9±1.630.5±5.342.7±7.40.35±0.07

86*64±637.7±1.67.0±1.55.9±5.68.3±7.90.84±0.82

87*46±307.8±1.67.1±1.48.4±5.211.7±7.30.60±0.39

88*>10511.4±1.710.4±1.5<5.3<7.5>1.38

89*>9210.8±1.89.8±1.6<5.8<8.1>1.22

90*>789.0±1.78.2±1.5<5.7<8.0>1.03

91*>899.9±1.79.0±1.5<5.5<7.7>1.17

92*>849.5±1.88.7±1.6<5.6<7.8>1.11

93*>798.8±1.78.0±1.5<5.5<7.7>1.05

94*>648.0±1.77.3±1.6<6.1<8.6>0.85

95*>798.5±1.67.7±1.5<5.3<7.4>1.05

96*56±2513.5±1.712.3±1.511.8±5.016.5±7.00.74±0.33

97*46±2310.2±1.69.3±1.510.9±5.115.3±7.20.61±0.30

98*58±2614.8±1.713.4±1.612.6±5.517.6±7.70.76±0.34

99*64±518.7±1.57.9±1.46.7±5.29.4±7.30.84±0.67

100*58±587.1±1.76.4±1.66.0±5.78.3±8.00.77±0.76

101*>9810.2±1.79.3±1.5<5.1<7.2>1.29

102*50±417.6±1.76.9±1.67.4±5.710.4±8.00.66±0.54

10383±6311.2±1.610.2±1.56.7±5.09.3±6.91.09±0.82

104170±12822.3±1.720.3±1.56.5±4.99.1±6.82.24±1.69

105*>596.5±1.65.9±1.5<5.4<7.6>0.78

106*>10010.2±1.69.3±1.5<5.0<7.1>1.32

107*>9210.1±1.69.2±1.4<5.4<7.6>1.21

108*93±6913.4±1.512.2±1.47.1±5.29.9±7.21.23±0.90

109*37±1710.9±2.09.9±1.814.6±6.120.4±8.60.48±0.22

110*16±58.4±1.97.6±1.725.1±5.435.2±7.60.22±0.07

111*17±412.6±1.911.5±1.736.8±6.151.5±8.50.22±0.05

112*59±488.8±1.78.0±1.67.4±5.910.3±8.20.78±0.64

113*>9210.5±1.79.6±1.5<5.6<7.9>1.21

114*>15518.1±1.816.5±1.6<5.8<8.1>2.04

115*45±926.0±1.723.6±1.628.3±5.139.6±7.10.60±0.11

116*23±116.3±1.65.7±1.513.8±5.419.3±7.60.30±0.14

11725±1011.4±2.310.4±2.122.9±7.732.1±10.80.32±0.13

118*94±4522.8±1.720.7±1.511.9±5.716.7±8.01.24±0.60

11925±128.2±2.07.5±1.816.5±6.923.1±9.60.32±0.16

a Asterisks denote the statistical sample.

b Errors and lower-limits represent1σsigni?cance.

c The UV continuum luminosity atλ=1270?A.

10Murayama et al.

Fig.1.—Diagram between iz?NB816and NB816for all objects detected with NB816<26.Our LAE candidates are shown by?lled circles(the statistical sample)and open circles(the non-statistical sample).Objects with iz?NB816>2are shown at iz?NB816=2for clarity.The vertical line shows the detection limit of NB816=25.1.The horizontal line shows the selection criterion of iz?NB816=0.7. The curve shows the3σlimit for the iz?NB816color.

LYMANαEMITTERS AT z=5.711

B g′V r′i′NB816z′

1*

2*

3*

4*

5*

6*

7*

8*

9*

10*

Fig. 2.—Broad-band and NB816images of our LAE candidates at z≈5.7.Asterisks at the object number denote the statistical sample.Each box is12′′on a side(north is up and east is left).Each circle has3′′radius.

12Murayama et al.

B g′V r′i′NB816z′

11

12*

13*

14*

15*

16*

17*

18*

19*

20*

Fig.2.—continued.

LYMANαEMITTERS AT z=5.713

B g′V r′i′NB816z′

21*

22

23*

24*

25*

26*

27*

28*

29*

30*

Fig.2.—continued.

14Murayama et al.

B g′V r′i′NB816z′

31*

32

33*

34*

35*

36*

37*

38*

39*

40*

Fig.2.—continued.

LYMANαEMITTERS AT z=5.715

B g′V r′i′NB816z′

41*

42*

43*

44*

45*

46*

47*

48*

49*

50*

Fig.2.—continued.

16Murayama et al.

B g′V r′i′NB816z′

51*

52*

53*

54*

55*

56*

57*

58*

59*

60*

Fig.2.—continued.

LYMANαEMITTERS AT z=5.717

Fig.2.—continued.

18Murayama et al.

B g′V r′i′NB816z′

71*

72*

73*

74*

75*

76*

77*

78*

79*

80*

Fig.2.—continued.

LYMANαEMITTERS AT z=5.719

B g′V r′i′NB816z′

81*

82*

83*

84*

85*

86*

87*

88*

89*

90*

Fig.2.—continued.

20Murayama et al.

B g′V r′i′NB816z′

91*

92*

93*

94*

95*

96*

97*

98*

99*

100*

Fig.2.—continued.

可能性推理——数据比例之样本比例

可能性推理——数据比例之样本比例版权所有翻印必究 中公金融人出品 可能性推理是判断推理题型中比重与难度均较大的一类题型。这类题型的特点是题干给出一定的数据或者比例,以这些数据或比例为前提,得出一个结论。涉及到数据比例的题目一般难度较大,其中样本比例与环境比例的关系是困扰考生的一大难题。接下来中公教育专家就从例题出发,来总结一下出现样本比例的题目应该如何破题: 【例1】:某咨询机构的调查报告显示,近几年在某科技园区内的高收入人群中,硕士 及以上学历的人数占比达到70%,该咨询机构得出结论,本科及以下学历人群在该高科技园 区内要获得高收入比较困难。 下列哪项如果为真,能作为上述结论的前提? A. 本科及以下学历人群占该高科技园区职工总数的比例高达40% B. 本科及以下学历人群占该高科技园区职工总数的比例不足30% C. 该高科技园区低收入人群中,本科及以下学历人群占40% D. 该高科技园区低收入人群中,本科及以下学历人群占比不足30% 【中公解析】:题干由“近几年在某科技园区内的高收入人群中,硕士及以上学历的人 数占比达到 70%”,得出结论“本科及以下学历人群在该高科技园区内要获得高收入比较困 难”。题干的高收入人群可以作为样本,其中硕士及以上比例为70%,本科及以下应为30%, 仅仅通过样本的比例无法说明结论,得出结论需考虑环境即整体中的比例。C、D选项通过 列举了低收入人群的比例,同样是引用样本比例来论证,不能得出结论。A、B选项涉及到 了环境即整体的比例,A选项说明在所有职工中本科及以下占40%,高于样本中本科及以下 学历的30%,我们认为从环境到样本,本科及以下所占比例下降了,本科及以下的特质对获 得高收入起到了负作用,可以得出结论本科及以下学历获得高收入比较困难。故答案选 A。 【例2】:据调查,某地 90%以上有过迷路经历的司机都没有安装车载卫星导航系统。 这表明,车载卫星导航系统能有效防止司机迷路。 以下最能削弱上述论证的一项是( )

抽样调查样本量确定

抽样调查样本量的确定 在贸易统计中, 对于限额以下批零餐饮企业普遍采用抽样调查方法进行解决。然而,由于当前市场经济情况的多样性,经济发展的不均衡性,以及地域宽广性,导致情况多种多样;实际情况的复杂,决定了方案的复杂性,增加了具体抽样的难度。经过多年的探讨,区域二相抽样调查比较符合当前我国的实际情况,我们在这里根据试点所掌握的情况针对采用区域二相抽样调查的贸易抽样方案中如何确定样本量进行分析。 一、样本单位数量的确定原则 一般情况下,确定样本量需要考虑调查的目的、性质和精度要求。以及实际操作的可行性、经费承受能力等。根据调查经验,市场潜力和推断等涉及量比较严格的调查需要的样本量比较大,而一般广告效果等人们差异不是很大或对样本量要求不是很严格的调查,样本量相对可以少一些。实际上确定样本量大小是比较复杂的问题,即要有定性的考虑,也要有定量的考虑;从定性的方面考虑,决策的重要性、调研的性质、数据分析的性质、资源、抽样方法等都决定样本量的大小。但是这只能原则上确定样本量大小。具体确定样本量还需要从定量的角度考虑。 从定量的方面考虑,有具体的统计学公式,不同的抽样方法有不同的公式。归纳起来,样本量的大小主要取决于: (1)研究对象的变化程度,即变异程度; (2)要求和允许的误差大小,即精度要求; (3)要求推断的置信度,一般情况下,置信度取为95%; (4)总体的大小; (5)抽样的方法。 也就是说,研究的问题越复杂,差异越大时,样本量要求越大;要求的精度越高,可推断性要求越高时,样本量也越大;同时,总体越大,样本量也相对要大,但是,增大呈现出一定对数特征,而不是线形关系;而抽样方法问题,决定设计效应的值,如果我们设定简单随机抽样设计效应的值是1;分层抽样由于抽样效率高于简单随机抽样,其设计效应的值小于1,合适恰当的分层,将使层内样本差异变小,层内差异越小,设计效应小于1的幅度越大;多阶抽样由于效率低于简单随机抽样,设计效应的值大于1,所以抽样调查方法的复杂程度决定其样本量大小。对于不同城市,如果总体不知道或很大,需要进行推断时,大城市多抽,小城市少抽,这种说法原则上是不对的。实际上,在大城市抽样太大是浪费,在小城市抽样太少没有推断价值。

Minitab-单样本比率详解

https://www.sodocs.net/doc/f017788502.html, MINITAB ASSISTANT WHITE PAPER This paper explains the research conducted by Minitab statisticians to develop the methods and data checks used in the Assistant in Minitab 17 Statistical Software. 1-Sample % Defective Test Overview A test for 1-proportion is used to determine whether a proportion differs from a target value. In quality analysis, the test is often used when a product or service is characterized as defective or not defective to determine whether the percentage of defective items significantly differs from a target % defective. The Minitab Assistant includes a 1-Sample % Defective Test. The data collected for the test are the number of defective items in a sample, which is assumed to be the observed value of a binomial random variable. The Assistant uses exact methods to calculate the hypothesis test results and the confidence intervals; therefore, the actual Type I error rate should be near the level of significance (alpha) specified for the test and no further investigation is required. However, the power and sample size analysis for the 1-Sample % Defective test is based on an approximation and we need to evaluate it for accuracy. In this paper we investigate the methodology used to evaluate power and sample size for the 1-sample % defective test, comparing the theoretical power of the approximate method with the actual power of the exact test. We also describe how we established a guideline to help you evaluate whether your sample size is large enough to detect whether the percentage of defective items differs from a target % defective. The Assistant automatically performs a check on the sample size and reports the findings in the Report Card. The 1-Sample % Defective Test also depends on other assumptions. See Appendix A for details.

示范教案( 用样本的数字特征估计总体的数字特征)

2.2.2 用样本的数字特征估计总体的数字特征 整体设计 教学分析 教科书结合实例展示了频率分布的众数、中位数和平均数.对于众数、中位数和平均数的概念,重点放在比较它们的特点,以及它们的适用场合上,使学生能够发现,在日常生活中某些人通过混用这些(描述平均位置的)统计术语进行误导.另一方面,教科书通过思考栏目让学生注意到,直接通过样本计算所得到的中位数与通过频率直方图估计得到的中位数不同.在得到这个结论后,教师可以举一反三,使学生思考对于众数和平均数,是否也有类似的结论.进一步,可以解释对总体众数、总体中位数和总体平均数的两种不同估计方法的特点.在知道样本数据的具体数值时,通常通过样本计算中位数、平均值和众数,并用它们估计总体的中位数、均值和众数.但有时我们得到的数据是整理过的数据,比如在媒体中见到的频数表或频率表,用教科书中的方法也可以得到总体的中位数、均值和众数的估计. 教科书通过几个现实生活的例子,引导学生认识到:只描述平均位置的特征是不够的,还需要描述样本数据离散程度的特征.通过对如何描述数据离散程度的探索,使学生体验创造性思维的过程.教科书通过例题向学生展示如何用样本数字特征解决实际问题,通过阅读与思考栏目“生产过程中的质量控制图”,让学生进一步体会分布的数字特征在实际中的应用. 三维目标 1.能利用频率分布直方图估计总体的众数、中位数、平均数;能用样本的众数、中位数、平均数估计总体的众数、中位数、平均数,并结合实际,对问题作出合理判断,制定解决问题的有效方法;初步体会、领悟“用数据说话”的统计思想方法;通过对有关数据的搜集、整理、分析、判断,培养学生“实事求是”的科学态度和严谨的工作作风. 2.正确理解样本数据标准差的意义和作用,学会计算数据的标准差;能根据实际问题的需要合理地选取样本,从样本数据中提取基本的数字特征(如平均数、标准差),并作出合理的解释;会用样本的基本数字特征估计总体的基本数字特征,形成对数据处理过程进行初步评价的意识. 3.在解决统计问题的过程中,进一步体会用样本估计总体的思想,理解数形结合的数学思想和逻辑推理的数学方法;会用随机抽样的方法和样本估计总体的思想解决一些简单的实际问题,认识统计的作用,能够辨证地理解数学知识与现实世界的联系. 重点难点 教学重点:根据实际问题对样本数据中提取基本的数据特征并作出合理解释,估计总体的基本数字特征;体会样本数字特征具有随机性. 教学难点:用样本平均数和标准差估计总体的平均数与标准差;能应用相关知识解决简单的实际问题. 课时安排 2课时 教学过程 第1课时众数、中位数、平均数 导入新课 思路1 在一次射击比赛中,甲、乙两名运动员各射击10次,命中环数如下﹕ 甲运动员:7,8,6,8,6,5,8,10,7,4; 乙运动员:9,5,7,8,7,6,8,6,7,7. 观察上述样本数据,你能判断哪个运动员发挥得更稳定些吗?为了从整体上更好地把握总体的规律,我们要通过样本的数据对总体的数字特征进行研究.——用样本的数字特征估计

样本的选取

4.2样本的选取 学习目标:1、在具体情境中,体会不同的抽样可能得到不同的结果,感受选择抽样方法的重要性。 2、结合实际问题,理解样本必须具有代表性。 3、了解抽样调查的基本思想是“用局部估计总体”。 重点:样本容量越大,样本特性就越接近总体特性。 难点:怎样选取合适的样本容量 课前准备 温故知新: 1、普查与抽样调查的区别?并举例说明什么时候用普查的方式获得数据比较好,什么时候用抽样调查的方式获得数据比较好. 2、品尝一勺汤,就可以知道一锅汤的味道,你知道其中蕴涵的道理吗? : 为了了解你所在地区老年人的健康状况,小明、小颖、小华三位同学分别采取了下列调查方式:小明:在公园里调查了1000名老年人,他们一年中生病的次数如表一: 表一 小颖:在医院调查了1000名老年病人,他们一年中生病的次数如表二: 表二 问题1:比较一下小明与小颖所得数据的差别,是什么原因造成的? 小华:调查了10名老年邻居,他们一年中生病的次数如下表所示:问题2:你同意他们三个人的做法吗?说明你的理由. 你认为抽样调查时应注意什么? 二. 交流展示: (一)活动一:自学课本第93页并回答下列问题 为了了解本校初中学生暑假期间参加体育活动的情况,,学校准备抽取一部分学生进行问卷调查。现有三个发放调查问卷的方案:: 方案1:发给学校田径队的30名同学; 方案2:从每个班级抽取一名同学; 方案3:从每个班级中抽取学号分别为1,11,21,31,41的五名同学。 (1)本次调查中的总体是什么?样本是什么?样本容量是多少? (2) 采用哪个方案发放问卷比较合理呢?我们为何选择这个方案呢? 活动三:例题解析 例1:判断下面这些抽样调查选取样本的方法是否合适,若不合适,请说明理由。 (1)为调查江苏省的环境污染情况,调查了长江以南的南京市、常州市、苏州市、镇江市、无锡市的环境污染情况 (2)从100名学生中,随机抽取2名学生,测量他们的身高来估算这100名学生的平均身高. (3)从一批灯泡中随机抽取50个进行试验,估算这批灯泡的使用寿命. (4)为了解观众对中央电视台第一套节目的收视率,对所有上英特网的家庭进行在线调查.

样本数值特征估计总体数字特征

2.2.2用样本的数字特征估计总体的数字特征 整体设计 教学分析 教科书结合实例展示了频率分布的众数、中位数和平均数.对于众数、中位数和平均数的概念,重点放在比较它们的特点,以及它们的适用场合上,使学生能够发现,在日常生活中某些人通过混用这些(描述平均位置的)统计术语进行误导.另一方面,教科书通过思考栏目让学生注意到,直接通过样本计算所得到的中位数与通过频率直方图估计得到的中位数不同.在得到这个结论后,教师可以举一反三,使学生思考对于众数和平均数,是否也有类似的结论.进一步,可以解释对总体众数、总体中位数和总体平均数的两种不同估计方法的特点.在知道样本数据的具体数值时,通常通过样本计算中位数、平均值和众数,并用它们估计总体的中位数、均值和众数.但有时我们得到的数据是整理过的数据,比如在媒体中见到的频数表或频率表,用教科书中的方法也可以得到总体的中位数、均值和众数的估计. 教科书通过几个现实生活的例子,引导学生认识到:只描述平均位置的特征是不够的,还需要描述样本数据离散程度的特征.通过对如何描述数据离散程度的探索,使学生体验创造性思维的过程.教科书通过例题向学生展示如何用样本数字特征解决实际问题,通过阅读与思考栏目“生产过程中的质量控制图”,让学生进一步体会分布的数字特征在实际中的应用. 三维目标 1.能利用频率分布直方图估计总体的众数、中位数、平均数;能用样本的众数、中位数、平均数估计总体的众数、中位数、平均数,并结合实际,对问题作出合理判断,制定解决问题的有效方法;初步体会、领悟“用数据说话”的统计思想方法;通过对有关数据的搜集、整理、分析、判断,培养学生“实事求是”的科学态度和严谨的工作作风. 2.正确理解样本数据标准差的意义和作用,学会计算数据的标准差;能根据实际问题的需要合理地选取样本,从样本数据中提取基本的数字特征(如平均数、标准差),并作出合理的解释;会用样本的基本数字特征估计总体的基本数字特征,形成对数据处理过程进行初步评价的意识. 3.在解决统计问题的过程中,进一步体会用样本估计总体的思想,理解数形结合的数学思想和逻辑推理的数学方法;会用随机抽样的方法和样本估计总体的思想解决一些简单的实际问题,认识统计的作用,能够辨证地理解数学知识与现实世界的联系. 重点难点 教学重点:根据实际问题对样本数据中提取基本的数据特征并作出合理解释,估计总体的基本数字特征;体会样本数字特征具有随机性. 教学难点:用样本平均数和标准差估计总体的平均数与标准差;能应用相关知识解决简单的实际问题. 课时安排 2课时 教学过程 第1课时众数、中位数、平均数 导入新课 思路1 在一次射击比赛中,甲、乙两名运动员各射击10次,命中环数如下﹕ 甲运动员:7,8,6,8,6,5,8,10,7,4; 乙运动员:9,5,7,8,7,6,8,6,7,7. 观察上述样本数据,你能判断哪个运动员发挥得更稳定些吗?为了从整体上更好地把握总体的规律,我们要通过样本的数据对总体的数字特征进行研究.——用样本的数字特征估计总体

工程塑料特性样本

一、 PBT:聚对苯二甲酸丁二醇酯 聚对苯二甲酸丁二醇酯, 英文名polybutylece terephthalate( 简称PBT) , 属于聚酯系列, 是由1.4-丁二醇(1.4-Butylene glycol)与对苯二甲酸(PTA)或者对苯二甲酸酯(DMT)聚缩合而成, 并经由混炼程序制成的乳白色半透明到不透明、结晶型热塑性聚酯树脂。与PET一起统称为热塑性聚酯, 或饱和聚酯。 PBT理化特性 PBT为乳白色半透明到不透明、结晶型热塑性聚酯。具有高耐热性、韧性、耐疲劳性, 自润滑、低摩擦系数, 耐候性、吸水率低, 仅为0.1%, 在潮湿环境中仍保持各种物性( 包括电性能) , 电绝缘性, 但体积电阻、介电损耗大。耐热水、碱类、酸类、油类、但易受卤化烃侵蚀, 耐水解性差, 低温下可迅速结晶, 成型性良好。缺点是缺口冲击强度低 , 成型收缩率大。故大部分采用玻璃纤维增强或无机填充改性, 其拉伸强度、弯曲强度可提高一倍以上, 热变形温度也大幅提高。能够在140℃下长期工作, 玻纤增强后制品纵、横向收缩率不一致, 易使制品发生翘曲。 PBT加工工艺 PBT又可称为热塑性聚酯塑料, 为适用于不同加工业者使用, 一般多少会加入添加剂, 或与其它塑料掺混, 随着添加物比例不同, 可制造不同规格的产品。由于PBT具有耐热性、耐候性、耐药品性、电气特性佳、吸水性小、光泽良好, 广泛应用于电子电器、汽车零件、机械、家用品等, 而PBT产品又与PPE、 PC、 POM、 PA等共称为五大泛用工程塑料。 PBT 结晶速度快, 最适宜加工方法为注塑, 其它方法还有挤出、吹塑、涂覆和各种二次加工成型, 成型前需预干燥, 水分含量要降至0.02%。 PBT的注塑工艺特性与工艺参数的设定:

《用样本的数字特征估计总体的数字特征》教案

《用样本的数字特征估计总体的数字特征》教案 教学目标 1.能从样本数据中提取基本的数字特征,并做出合理的解释. 2.会求样本的众数、中位数、平均数. 3.能从频率分布直方图中,求得众数、中位数、平均数. 教学重难点 教学重点:用样本众数,中位数,平均数估计总体的众数,中位数,平均数.. 教学难点:用样本的数字特征估计总体的数字特征,统计思维的建立. 教学过程 情境导学 美国NBA 在2011——2012年度赛季中,甲、乙两名篮球运动员在随机抽取的12场比赛中的得分情况如下:甲运动员得分:12,15,20,25,31,30, 36,36,37,39,44,49;乙运动员得分:8,13,14,16,23,26, 28,38,39,51,31,39.如果要求我们根据上面的数据,估计、比较甲,乙两名运动员哪一位发挥得比较稳定,就应有相应的数据作为比较依据,即通过样本数字特征对总体的数字特征进行研究.所以今天我们开始学习用样本的数字特征估计总体的数字特征. 探究点一 众数、中位数和平均数 问题 在初中我们学过众数、中位数和平均数的概念,它们都是描述一组数据的集中趋势的特征数,只是描述的角度不同,你还能回忆起众数、中位数和平均数的定义及特点吗? 思考1 众数是如何定义的?有什么特点?举例加以说明. 答 众数:在一组数据中,出现次数最多的数据叫做这组数据的众数.特点:(1)众数是这组数据中出现次数最多的数;(2)众数可以有一个或多个; 如:一组数据为2,2,3,4,4,5,5,6,7,8;众数为2,4,5. 思考2 中位数是如何定义的?有什么特点?举例加以说明. 答 中位数:将一组数据按大小依次排列,把处在最中间位置的一个数据(或最中间两个数据的平均数)叫做这组数据的中位数. 特点:(1)排序后找中位数;(2)中位数只有一个;(3)中位数不一定是这组数据中的数. 如:一组数据为2,2,3,4,4,5,5,6,7,8;中位数为1 2 (4+5)=4.5.

用样本的数字特征估计总体的数字特征(高考题)【精选】

2.2.2用样本的数字特征估计总体的 数字特征 链接高考 1.(2014课标Ⅰ,18,12分,★★☆)从某企业生产的某种产品中抽取100件,测量这些产品的一项质量指标值,由测量结果得如下频数分布表: 质量指标值分组[75,85) [85,95) [95,105) [105,115) [115,125) 频数 6 26 38 22 8 (1)作出这些数据的频率分布直方图; (2)估计这种产品质量指标值的平均数及方差(同一组中的数据用该组区间的中点值作代表); (3)根据以上抽样调查数据,能否认为该企业生产的这种产品符合“质量指标值不低于95的产品至少要占全部产品80%”的规定? 2.(2014陕西,9,5分,★★☆)某公司10位员工的月工资(单位:元)为x1,x2, (x10) 其均值和方差分别为和s2,若从下月起每位员工的月工资增加100元,则这10位员工下月工资的均值和方差分别为() A.,s2+1002 B.+100,s2+1002 C.,s2 D.+100,s2

3.(2015广东,17,12分,★★☆)某城市100户居民的月平均用电量(单位:度),以[160,180),[180,200),[200,220),[220,240),[240,260),[260,280),[280,300]分组的频率分布直方图如图. (1)求直方图中x的值; (2)求月平均用电量的众数和中位数; (3)在月平均用电量为[220,240),[240,260),[260,280),[280,300]的四组用户中,用分层抽样的方法抽取11户居民,则月平均用电量在[220,240)的用户中应抽取多少户? 4.(2014课标Ⅱ节选,19,★★☆)某市为了考核甲、乙两部门的工作情况,随机访问了50位市民.根据这50位市民对这两部门的评分(评分越高表明市民的评价越高),绘制茎叶图如下: 甲部门乙部门 4 97 97665332110 98877766555554443332100 6655200 632220 3 4 5 6 7 8 59 0448 122456677789 011234688 00113449 123345

样本特征、描述统计分析模板

购买意愿willingness 382 0.727 0.446 0 1 认知与信任度trust 382 2.015 0.706 1 3 price 382 0.496 0.500 0 1 health 382 0.421 0.494 0 1 energy 382 1.992 0.768 1 3 0.498 0 1 exhau 382 0.452 quality 382 2.259 0.654 1 3 label 382 0.513 0.500 0 1 speed 382 2.172 0.757 1 3 信息来源source2 382 0.269 0.444 0 1 source3 382 0.256 0.437 0 1 source4 382 0.164 0.371 0 1 source5 382 0.104 0.306 0 1 family 382 0.493 0.501 0 1 info 382 0.513 0.500 0 1 friend 382 0.403 0.491 0 1 信息正反性exper 382 0.486 0.500 0 1 易得性promo 382 0.473 0.499 0 1 avail 382 0.413 0.493 0 1 个人特征age 382 34.018 11.718 18 62 gender 382 0.497 0.501 0 1 marital 382 0.536 0.499 0 1 income 382 37.448 16.212 2.3 98 employ2 382 0.261 0.440 0 1 employ3 382 0.232 0.423 0 1 数据来源:本研究计算整理,2013. 5.3样本描述统计分析 5.3.1被调查消费者基本情况 5.3.1.1被调查消费者年龄情况 如图5-1所示,根据调查结果,被调查的消费者中,25岁以下的有77人,占被调查对象的20%;25到35岁的被调查消费者较多为153人,占了40%;35到45岁的68人,占了18%;45到55岁的53人,占了14%;55岁及以上的31人,占了8%。

样本容量确定

11 第三节 样本容量的确定 在区间估计中我们发现,对于某一个总体的参数进行估计时,在样本数目一定的条件下,要提高估计结果的可靠性,就需要扩大置信区间,这就要增加估计中的误差,减少了估计的实际意义。如果要减少估计的误差,就要缩短置信区间,但这样就必须要降低估计的可靠性。可见在样本数目一定的条件下,估计的精确性和估计的可靠性不能两全其美。既要提高估计的精确性,减少误差,又要提高估计可靠性的办法就是增加样本容量。但是增加样本就要同时增加抽样调查的成本,同时又可能延误时间。因此就需要研究能够满足对估计的可靠性和精确性要求的最小样本数问题。 一、均值估计问题中,样本大小的决定 在总体均值的估计问题中,要决定必要的样本大小,必须先明确如下三个问题: 1. 要规定允许的估计误差的大小,即允许的估计值与实际值之间的最大偏离值是多少,实际上也就是估计区间的大小, 2. 规定置信度,即估计所要求达到的可靠性,也就是实际的抽样误差不超过所规定的误差的可信度。 3. 要明确总体的标准差,即要求了解总体的分布情况。总体的标准差小,只要抽较少的样本就能满足对估计精确度和可靠性的要求,若总体标准差大,就必须抽取较多的样本才能达到对估计精确度和可靠性的要求。 设总体标准差为σ,样本均值的标准差为x σ。估计的置信度为1-α,于是可以 相应地得到置信系数Z α/2。于是对总体均值的估计可由下式得到: ()P X Z x -

样本量的确定方法.

样本量的确定方法(2008-10-14 09:12:34) 一、样本单位数量的确定原则 一般情况下,确定样本量需要考虑调查的目的、性质和精度要求。以及实际操作的可行性、经费承受能力等。根据调查经验,市场潜力和推断等涉及量比较严格的调查需要的样本量比较大,而一般广告效果等人们差异不是很大或对样本量要求不是很严格的调查,样本量相对可以少一些。实际上确定样本量大小是比较复杂的问题,即要有定性的考虑,也要有定量的考虑;从定性的方面考虑,决策的重要性、调研的性质、数据分析的性质、资源、抽样方法等都决定样本量的大小。但是这只能原则上确定样本量大小。具体确定样本量还需要从定量的角度考虑。 从定量的方面考虑,有具体的统计学公式,不同的抽样方法有不同的公式。归纳起来,样本量的大小主要取决于: (1)研究对象的变化程度,即变异程度; (2)要求和允许的误差大小,即精度要求; (3)要求推断的置信度,一般情况下,置信度取为95%; (4)总体的大小; (5)抽样的方法。 也就是说,研究的问题越复杂,差异越大时,样本量要求越大;要求的精度越高,可推断性要求越高时,样本量也越大;同时,总体越大,样本量也相对要大,但是,增大呈现出一定对数特征,而不是线形关系;而抽样方法问题,决定设计效应的值,如果我们设定简单随机抽样设计效应的值是1;分层抽样由于抽样效率高于简单随机抽样,其设计效应的值小于1,合适恰当的分层,将使层内样本差异变小,层内差异越小,设计效应小于1的幅度越大;多阶抽样由于效率低于简单随机抽样,设计效应的值大于1,所以抽样调查方法的复杂程度决定其样本量大小。对于不同城市,如果总体不知道或很大,需要进行推断时,大城市多抽,小城市少抽,这种说法原则上是不对的。实际上,在大城市抽样太大是浪费,在小城市抽样太少没有推断价值。 二、样本量的确定方法 如何确定样本量,基本方法很多,但是公式检验表明,当误差和置信区间一定时,不同的样本量计算公式计算出来的样本量是十分相近的,所以,我们完全可以使用简单随机抽样计算样本量的公式去近似估计其他抽样方法的样本量,这样可以更加快捷方便,然后将样本量根据一定方法分配到各个子域中去。所以,区域二相抽样不能计算样本量的说法是不科学的。

样本特征描述统计分析模板

表5-4 变量描述统计表 变量类型变量样本数均值标准差最小值最大值购买意愿willingness 382 0.727 0.446 0 1 认知与信任度trust 382 2.015 0.706 1 3 price 382 0.496 0.500 0 1 health 382 0.421 0.494 0 1 energy 382 1.992 0.768 1 3 exhau 382 0.452 0.498 0 1 quality 382 2.259 0.654 1 3 label 382 0.513 0.500 0 1 speed 382 2.172 0.757 1 3 信息来源source2 382 0.269 0.444 0 1 source3 382 0.256 0.437 0 1 source4 382 0.164 0.371 0 1 source5 382 0.104 0.306 0 1 family 382 0.493 0.501 0 1 info 382 0.513 0.500 0 1 friend 382 0.403 0.491 0 1 信息正反性exper 382 0.486 0.500 0 1 易得性promo 382 0.473 0.499 0 1 avail 382 0.413 0.493 0 1 个人特征age 382 34.018 11.718 18 62 gender 382 0.497 0.501 0 1 marital 382 0.536 0.499 0 1 income 382 37.448 16.212 2.3 98 employ2 382 0.261 0.440 0 1 employ3 382 0.232 0.423 0 1 数据来源:本研究计算整理,2013. 5.3样本描述统计分析 5.3.1被调查消费者基本情况 5.3.1.1被调查消费者年龄情况 如图5-1所示,根据调查结果,被调查的消费者中,25岁以下的有77人,占被调查对象的20%;25到35岁的被调查消费者较多为153人,占了40%;35到45岁的68人,占了18%;45到55岁的53人,占了14%;55岁及以上的31人,占了8%。

样本特征数

样本特征数 第三章 样本特征数 第一节 集中位置量数 【教学目的】1、使学生了解集中位置量数的含义,并能正确理解。 2、掌握平均数、中位数的计算方法,并能熟练运用。 3、了解什么是众数。 【教学重点】平均数、中位数的计算 【教学难点】对组序差的理解 【导言】 集中位置量数:反映数据集中趋势的特征数 离中位置量数:反映数据离中趋势的特征数 集中位置量数与离中位置量数统称为样本特征数,只有当两者结合起来描述样本的特征时,才能全面地认识样本数量的特征。 【教学内容】 一、 平均数(算术平均数) (一)小样本资料平均数的计算(n ≤45) 1、直接法: n x x ∑= 【举例】10人肺活量(ml ) 2600 3400 2700 2400 2800 3050 2950 2550 2500 3000 )(279510 3000 34002600ml n x x =+++= = ∑ 2、简化法(假定均数法):适用于样本变量位数多或带小数的资料。 n x A x ∑'+ =

关于A 的几点说明: (1)A越接近均数,计算越简单。 (2)尽量选整数,若不能选整数,也要尽量选整齐的数。 (二)大样本资料平均数的计算(n >45) (假定均数法) i n fd A x ∑ + = A— 假定均数,从理论上讲,A可以取任何一个常数,但为了计 算方便,一般选取频数最多的那组的组中值x '。 d — 组序差(缩减值或简化后的组中值) i A x d -'= 由于等距 分组(即i 相等), d 值是有规律的,A 所在组d =0,向上依次是-1,-2,-3……..向下依次为1,2,3……。 【举例】120名18岁女孩身高如下表,求x 。 i n fd A x ∑ + = =160+ 2 120 17?- =159.7(cm ) 【注意】此方法在样本含量不大时, x 有一定偏差(各组的x '代替了 各组的实测值)随着样本含量的增大,精确度也会随着提高。 组限 f x ' d fd 147~ 149~ 151~ 153~ 155~ 157~ 159~ 161~ 163~ 165~ 167~ 169~ 171~ 1 -6 -6 4 -5 -20 8 -4 -32 11 -3 -33 14 -2 -28 15 -1 -15 20 160 0 0 15 1 15 11 2 22 10 3 30 6 4 24 4 5 20 1 6 6 ∑ 120 -17

统计初步——用样本的`数据特征描述数据(一)

§6.2.2 用样本的数据特征描述数据(一) 一、教学目标 1、知识与技能:了解方差、标准差的概念及引入这两个概念的意义,会根据定义计算 一组数据的方差和标准差,知道方差和标准差是衡量一组数据离散程度的量,会根据方差和标准差的大小,比较与判断具体问题中有关数据的离散程度。 2、过程与方法:通过学生的探索、讨论、动手计算,从不同的角度去分析、处理人们 在生产或生活中搜集的一组数据,培养学生创造性解决实际问题的能力。 3、情感态度与价值观:体会方差、标准差是反映一组数据波动大小的量,在数据的整 理与计算的过程中养成耐心、细致、认真的习惯,学会把知识应用于生活。 二、教学重点:通过实例理解样本标准差的意义和作用,学会计算样本标准差。 教学难点:理解样本标准差的意义和作用,形成对数据处理过程进行初步评价的意识。 三、教法:启发法,讨论法 教具:多媒体辅助教学 §6.2.2 用样本的数据特征描述数据(一) 例1 例2 五、教学过程 (一)情境导入 同学们认识照片中的男孩吗? 2004年雅典奥运会男子10米气步枪金牌,并以702.7环打破世界纪录;

温州籍奥运冠军,射击运动员——朱启南。 如果要选拔射击手参加射击比赛,应该挑选测试成绩中曾达到最好成绩的选手还是 成绩最稳定的选手? 学生活动:思考回答,自圆其说 总结:具体派谁去还要看具体情况,具体问题具体分析 顺势板书:§6.2.2 用样本的数据特征描述数据(一) (二)探究新知 → 观察与思考 从甲、乙两名学生中选拔一人参加射击比赛,对他们的射击水平进行了测试,两人 (1)甲、乙命中环数的平均数各是多少? 师: → n x x x x n +++= 21 生: → 747109568687101=+++++++++?= )(甲x 7776867875910 1=+++++++++?=)(乙x 应该派谁去? 甲和乙射击成绩的平均数都是7环,从平均数我们无法判断谁的成绩比较稳定。 平均数描述了数据的平均水平,定量地反映了数据的集中趋势所处的水平。 我们采用各偏差平方的平均数来衡量数据的稳定性,即 [] 222212)()()(1 x x x x x x n S n -++-+-= 叫做这组数据的方差(用S 2 来表示)。 1、方差是衡量数据稳定性的一个统计量; 2、方差的大小跟数据的大小有关,还跟数据的个数有关,所以我们比较两组数据的 稳定性时,应取相同的样本容量; 3、要求某组数据的方差,要先求数据的平均数; 4、方差的单位是所给数据单位的平方; 4、方差越大,波动越大,越不稳定;方差越小,波动越小,越稳定。 (2)甲、乙命中环数的方差各是多少? 学生完成后,教师点评,板书。 [] 374777107975767876787710 12 2222222222=-+-+-+-+-+-+-+-+-+-=)()()()()()()()()()(甲s

相关主题